Defocus correction coefficient determination method, CT image generation method and device

Abstract

The present application relates to a method for determining a focus correction coefficient, a CT image generation method and a device. The focus correction coefficient determination method includes: obtaining training data; the training data includes water phantom data obtained based on a first CT device; constructing a loss function based on a defocused water phantom image; the defocused water phantom image is a water phantom image with focus artifacts; using the water phantom data as the input of a pre-trained image generation model to obtain an output water phantom image based on the pre-trained image generation model; calculating the loss value of the output water phantom image based on the loss function, training the pre-trained image generation model until the loss value reaches a convergence threshold, and obtaining a fully trained image generation model; determining the focus correction coefficient of the first CT device based on the model parameters of the image generation model obtained through training. Through the present application, the automatic determination of the focus correction coefficient is achieved, reducing manpower and time costs.

Description

Technical Field

[0001] The present application relates to the field of image reconstruction technology, and in particular to a method for determining a focus correction coefficient, and a method and device for generating a CT image. Background Art

[0002] In CT equipment, the transmission of X-rays is affected by various factors, such as scattering from objects, scattering from the tube target surface, and errors in detector installation. These factors can cause focus artifacts in the image that affect clinicians' diagnoses.

[0003] In existing technologies, the focus correction coefficients of different CT detector modules are manually and iteratively adjusted to reduce related artifacts in reconstructed images. However, this method is time-consuming and labor-intensive, hindering product mass production and factory serviceability. Summary of the Invention

[0004] The embodiments of the present application provide a method for determining a focus correction coefficient, a method and apparatus for generating a CT image, so as to at least solve the problem in the related art that the process of manually iteratively adjusting the focus correction coefficient of the CT device is time-consuming and labor-intensive.

[0005] In a first aspect, an embodiment of the present application provides a method for determining a focus correction coefficient, comprising:

[0006] Acquire training data; the training data includes water model data acquired based on the first CT device;

[0007] Constructing a loss function based on a defocused water phantom image; wherein the defocused water phantom image is a water phantom image with defocus artifacts;

[0008] Using the water phantom data as input to a pre-trained image generation model to obtain an output water phantom image based on the pre-trained image generation model;

[0009] Calculating a loss value of the output water phantom image based on the loss function, training the pre-trained image generation model until the loss value reaches a convergence threshold, and obtaining a fully trained image generation model;

[0010] Determine a focus correction coefficient of the first CT device according to the model parameters of the image generation model obtained through training.

[0011] In some embodiments, constructing a loss function based on the off-focus water phantom image includes:

[0012] Acquire an off-focus water phantom image;

[0013] Segmenting the defocused water phantom image to obtain a water phantom main region and a water phantom wall region;

[0014] A loss function is constructed according to the difference in CT value distribution between the water phantom main region and the water phantom wall region.

[0015] In some embodiments, constructing a loss function based on the difference in CT value distribution between the water phantom main region and the water phantom wall region includes:

[0016] The standard deviation between the CT mean of the water phantom main region and the CT mean of the water phantom wall region is determined as the loss function.

[0017] In some embodiments, the CT mean value of the water phantom main body region and / or the CT mean value of the water phantom wall region is a pixel mean value of a preset number of pixel points in the corresponding region.

[0018] In some embodiments, determining the focus correction coefficient of the first CT device based on the model parameters of the image generation model obtained through training includes:

[0019] Obtaining corresponding model parameters according to the image generation model obtained through training, wherein the model parameters include weights and biases;

[0020] A focus correction coefficient of the first CT device is determined according to the weight and the offset.

[0021] In some embodiments, the pre-trained image generation model is an image generation model trained based on a second CT device; the first CT device and the second CT device are of the same type.

[0022] In a second aspect, an embodiment of the present application provides a CT image generation method, comprising:

[0023] Determine an image generation model corresponding to the first CT device based on the focus correction coefficient determination method as described in the first aspect above, and generate a CT image based on the image generation model; or,

[0024] The focus correction coefficient corresponding to the first CT device is determined based on the focus correction coefficient determination method as described in the first aspect above, and a CT image is generated based on the focus correction coefficient.

[0025] In a third aspect, an embodiment of the present application provides a device for determining a focus correction coefficient, comprising:

[0026] A training data acquisition unit, configured to acquire training data; the training data includes water modeling data acquired based on the first CT device;

[0027] A loss function construction unit, configured to construct a loss function based on a defocused water phantom image; the defocused water phantom image is a water phantom image with defocus artifacts;

[0028] an output water phantom image acquisition unit, configured to use the water phantom data as input to a pre-trained image generation model to obtain an output water phantom image based on the pre-trained image generation model;

[0029] a model training unit, configured to calculate a loss value of the output water phantom image based on the loss function, and train the pre-trained image generation model until the loss value reaches a convergence threshold, thereby obtaining a fully trained image generation model;

[0030] A focus correction coefficient determination unit is used to determine the focus correction coefficient of the first CT device according to the model parameters of the image generation model obtained through training.

[0031] In a fourth aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method for determining the focus correction coefficient as described in the first aspect above or the method for generating a CT image as described in the second aspect above is implemented.

[0032] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, it implements the method for determining the focus correction coefficient as described in the first aspect above or the method for generating a CT image as described in the second aspect above.

[0033] Compared with the related art, the embodiment of the present application provides a method for determining a focus correction coefficient, a method for generating a CT image, and a device. By using the water phantom data as the input of a pre-trained image generation model, an output water phantom image based on the pre-trained image generation model is obtained; the loss value of the output water phantom image is calculated based on the loss function, and the pre-trained image generation model is trained until the loss value reaches a convergence threshold, thereby obtaining a fully trained image generation model; the focus correction coefficient of the first CT device is determined based on the model parameters of the trained image generation model, thereby realizing automatic determination of the focus correction coefficient based on the fully trained image generation model, reducing the manpower and time cost of manual iterative adjustment, while reducing the focus artifacts of the image and improving the image generation quality.

[0034] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0036] Figure 1 is a flow chart of a method for determining a focus correction coefficient in one embodiment of the present application;

[0037] Figure 2 is a schematic diagram of a defocused water phantom image in one embodiment of the present application;

[0038] Figure 3 This is a schematic diagram of a process for constructing a loss function based on a defocused water phantom image in one embodiment of the present application;

[0039] Figure 4 yes Figure 2 Cross-section of the off-focus water phantom image shown;

[0040] Figure 5 is a schematic diagram of a flow chart for determining the focus correction coefficient of the first CT device in one embodiment of the present application;

[0041] Figure 6 This is a structural block diagram of a device for determining a focus correction coefficient in one embodiment of the present application;

[0042] Figure 7 It is a structural diagram of an electronic device in one of the embodiments of the present application.

[0043] Description of the accompanying drawings: 201, training data acquisition unit; 202, loss function construction unit; 203, output water model image acquisition unit; 204, model training unit; 205, focus correction coefficient determination unit; 30, bus; 31, processor; 32, memory; 33, communication interface. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely used to explain this application and are not intended to limit this application. Based on the embodiments provided in this application, all other embodiments obtained by those of ordinary skill in the art without making any creative efforts are within the scope of protection of this application.

[0045] Obviously, the drawings described below are merely examples or embodiments of the present application. Those skilled in the art can, without inventive effort, apply the present application to other similar scenarios based on these drawings. Furthermore, it is also understood that, although the effort involved in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, changes in design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as an insufficiency of the content disclosed in this application.

[0046] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0047] Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by a person of ordinary skill in the technical field to which this application belongs. The words "one", "a", "the" and the like used in this application do not indicate a limit on quantity and may indicate the singular or plural. The terms "include", "comprise", "have" and any variations thereof used in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units that are inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The word "multiple" used in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0048] The methods, devices, apparatus or computer-readable storage media involved in this application can be applied to non-invasive medical imaging devices for the purpose of disease diagnosis or research. The medical imaging device may include a single-modality scanner and / or a multi-modality scanner. A single-modality scanner may include a computed tomography (CT) system; a multi-modality scanner may include, for example, an X-ray imaging-magnetic resonance imaging (X-ray-MRI) scanner, a positron emission tomography-X-ray imaging (PET-X-ray) scanner, a single-photon emission computed tomography-magnetic resonance imaging (SPECT-MRI) scanner, a positron emission tomography-computed tomography (PETCT) scanner, etc. The scanners provided above are for illustrative purposes only and are not intended to limit the scope of this application.

[0049] The embodiments of the present application will be described below using a computed tomography system as an example.

[0050] This embodiment provides a method for determining a focus correction coefficient. Figure 1 is a flow chart of a method for determining a focus correction coefficient according to an embodiment of the present application. Figure 1 As shown, the process includes the following steps:

[0051] Step S101 : acquiring training data; the training data includes water modeling data acquired based on a first CT device.

[0052] In this embodiment, the medical imaging device is a first CT device, comprising a radiation source and a first CT detector. When acquiring water phantom data using the first CT detector, a water phantom (typically a circular container filled with water) is placed within the detection area of the medical imaging device, ensuring that the scanning range completely covers the water phantom. The radiation source in the medical imaging device emits radioactive rays toward the water phantom, and the first CT detector detects radiation events emanating from the detection area to obtain water phantom data.

[0053] After scanning and obtaining water model data, the water model data is used as training data for subsequent training of the image generation model. In some embodiments, water model scans can be performed in different scanning directions and with different water model specifications to obtain multiple sets of water model data as training data. In other embodiments, water model data can be obtained by scanning using different scanning parameters. For example, scanning parameters that are highly correlated with image focus artifact generation can be selected, such as selecting all water model data scanned using a combination of kV (peak tube voltage) and bowtie (environmental variables) as training data.

[0054] Step S102: constructing a loss function based on the off-focus water phantom image.

[0055] During the generation of water phantom images, X-ray transmission is affected by many factors, such as scattering of objects, scattering of the target surface of the radiation source tube, and errors in the installation process of the CT detector. These factors can easily lead to defocus artifacts in water phantom images. Figure 2 The figure shows a schematic diagram of a defocused water phantom image. The defocused water phantom image is a water phantom image with defocus artifacts, which are mainly manifested as black bands appearing near the water phantom wall. The appearance of defocus artifacts reduces the imaging quality of the medical imaging device.

[0056] In this embodiment, the main purpose of training the image generation model is to reduce focus artifacts. A loss function can be constructed based on the principle that larger focus artifacts in a defocused water phantom image correspond to larger loss function values, while smaller focus artifacts correspond to smaller loss function values. For example, a loss function can be constructed using artifact features of different regions in a defocused water phantom image. Artifact features can include differences in pixel value distribution, CT value distribution, and so on. This application does not limit the calculation method of the loss function.

[0057] Step S103: using the water phantom data as input to a pre-trained image generation model to obtain an output water phantom image based on the pre-trained image generation model.

[0058] Step S104: Calculate the loss value of the output water phantom image based on the loss function, train the pre-trained image generation model until the loss value reaches a convergence threshold, and obtain a fully trained image generation model.

[0059] In this embodiment, the water phantom data is used as the input of a pre-trained image generation model, and the corresponding output water phantom image is used as the output to train the pre-trained image generation model. By calculating the loss function of the output water phantom image, the calculated loss value is reduced to a convergence threshold, so as to continuously learn and adjust the model parameters in the network to obtain a fully trained image generation model. The pre-trained image generation model can be a neural network model based on deep learning, such as a Resnet network or a U-net network, etc., which is not limited in this application.

[0060] In some embodiments, reaching the convergence threshold can occur when the loss value of the output water phantom image reaches a preset threshold or remains unchanged. In other embodiments, to further improve the training effectiveness of the image generation model, reaching the convergence threshold can also occur when the sum of the loss values of the output water phantom images of all training data reaches a preset threshold or remains unchanged. At this point, it can be considered that the various network parameters in the model have reached stability, the image generation model has reached optimization, and training has concluded.

[0061] Step S105 : determining a focus correction coefficient of the first CT device according to the model parameters of the image generation model obtained through training.

[0062] In this embodiment, CT image generation based on the trained image generation model can reduce focus artifacts in CT images. Based on this image generation model, research has found that, without manually iteratively adjusting the focus correction coefficient of the first CT device, the focus correction coefficient of the first CT device can be determined by extracting model parameters from the trained image generation model and using the correlation between the pre-fitted model parameters and the focus correction coefficient. Correcting focus artifacts based on these focus correction coefficients can reduce focus artifacts in the generated images.

[0063] It is understood that the correlation between the model parameters and the focus correction coefficients can be pre-fitted and can be a parameter correction table or a function calculation formula, which is not limited in this application. In some embodiments, the first CT device includes a first CT detector, which includes multiple detection modules arranged in an arc shape. For different detector modules, the correlation between the model parameters and the focus correction coefficients of each detector module can be fitted separately. Based on this correlation and the model parameters of the image generation model obtained through training, the focus correction coefficients of the first CT device corresponding to different detection modules of the first CT detector can be determined.

[0064] In summary, the embodiments of the present application provide a method for determining a focus correction coefficient, a method for generating a CT image, and a device. By using the water phantom data as the input of a pre-trained image generation model, an output water phantom image based on the pre-trained image generation model is obtained; the loss value of the output water phantom image is calculated based on the loss function, and the pre-trained image generation model is trained until the loss value reaches a convergence threshold, thereby obtaining a fully trained image generation model; the focus correction coefficient of the first CT device is determined based on the model parameters of the trained image generation model, thereby realizing automatic determination of the focus correction coefficient based on the fully trained image generation model, reducing the manpower and time cost of manual iterative adjustment, while reducing the focus artifacts of the image and improving the image generation quality.

[0065] The embodiments of the present application are described and illustrated below through preferred embodiments.

[0066] like Figure 3 As shown, based on the above embodiments, in some embodiments, constructing a loss function based on the off-focus water phantom image includes:

[0067] Step S1021: Acquire a defocused water phantom image.

[0068] Step S1022 , segmenting the off-focus water phantom image to obtain a water phantom main region and a water phantom wall region.

[0069] Step S1023 : constructing a loss function based on the difference in CT value distribution between the water phantom main region and the water phantom wall region.

[0070] like Figure 4 Shown Figure 2 The cross-sectional view of the defocused water phantom image shown in the figure shows a difference in the CT value distribution between the main body and the wall of the water phantom. This is manifested as a black band near the wall and a certain decrease in CT values near the wall. Based on the above analysis, the defocused water phantom image can be segmented into the main body and wall regions. A loss function is constructed based on the difference in CT value distribution between the main body and wall regions. The main body region refers to the image region in the water phantom image where focus artifacts are not present at the center of the water phantom; the wall region refers to the image region near the wall where focus artifacts are present. Segmentation of the defocused water phantom image can be performed using threshold segmentation algorithms such as the OTSU (maximum between-class variance) method and the maximum entropy method.

[0071] In some embodiments, constructing a loss function based on the difference in CT value distribution between the main body region of the water phantom and the wall region of the water phantom includes determining the standard deviation between the CT mean of the main body region of the water phantom and the CT mean of the wall region of the water phantom as the loss function. Optionally, the CT mean of the main body region of the water phantom can be obtained by averaging the pixel values of pixels in the corresponding region, or by averaging the CT values of pixels in the corresponding region. The calculation can be performed on all pixels or a predetermined number of pixels, which is not limited in this application. Exemplarily, when calculating the pixel mean CT value, first, pixel values of all pixels in the main body region of the water phantom are obtained, and the pixel values of all pixels in the main body region of the water phantom are averaged to obtain a first CT mean of the main body region of the water phantom. Then, pixel values of 20 pixels in the wall region of the water phantom are obtained, and the pixel values of the 20 pixels in the wall region of the water phantom are averaged to obtain a second CT mean of the wall region of the water phantom. The standard deviation between the first and second CT mean values is determined as the loss function.

[0072] Of course, in other embodiments, the loss function may be constructed based on the difference in CT value distribution between the water phantom main region and the water phantom wall region, and the range, variance, etc. between the CT mean of the water phantom main region and the CT mean of the water phantom wall region may be determined as the loss function.

[0073] Through the above steps, a function was established to measure the difference between the water phantom wall region (i.e., the area with artifacts) and the water phantom main body region (i.e., the area without artifacts) in the off-focus artifact image generated by the image generation model. The parameters of the pre-trained image generation model were updated using this loss function to reduce the loss, so that the output water phantom images generated by the model tend to minimize off-focus artifacts, thus achieving the learning goal.

[0074] like Figure 5 As shown, based on the above embodiments, in some embodiments, determining the focus correction coefficient of the first CT device according to the model parameters of the image generation model obtained through training includes:

[0075] Step S1051: Obtain corresponding model parameters according to the image generation model obtained through training, where the model parameters include weights and biases.

[0076] Step S1052: Determine a focus correction coefficient of the first CT device according to the weight and the offset.

[0077] In some embodiments, the pre-trained image generation model is a deep neural network. When the image generation model is trained, the weights W and biases b of each neuron in the network can be set to random values close to 0, and an activation function is selected. The water phantom data is then used as the input of the pre-trained image generation model, and the corresponding output water phantom image is used as the output. After each layer of neuron operation (i.e., multiplied by the weights, added with the bias, and then operated by the activation function), the output of the first layer is used as the input of the second layer. The weights and biases in the neural network are continuously adjusted through training so that the loss value of the water phantom image output by the final output layer reaches the convergence threshold, thereby obtaining a fully trained image generation model.

[0078] By extracting the model parameter weights W and bias b of the image generation model, the focus correction coefficient of the first CT device can be determined according to the correlation between the model parameter weights W, bias b and the focus correction coefficient obtained by pre-fitting.

[0079] Based on the above embodiments, in some embodiments, the pre-trained image generation model is an image generation model trained based on a second CT device.

[0080] In this embodiment, an image generation model trained on a second CT device can be used as a pretrained image generation model for training the image generation model of the first CT device. By using the image generation model corresponding to the second CT device as the initial model for the first CT device, the training time for the image generation model corresponding to the first CT device can be significantly reduced. The second CT device is a device of the same type as the first CT device.

[0081] This embodiment also provides a CT image generation method, comprising: determining an image generation model corresponding to a first CT device based on the above-described method for determining a focus correction coefficient, and generating a CT image based on the image generation model. Specifically, scan data of a scanned object is first obtained, and an image generation model trained on the first CT device is obtained based on the above-described method for determining a focus correction coefficient. The scan data is used as input to the image generation model to generate a CT image, which is an image that has undergone focus artifact correction.

[0082] This embodiment also provides a CT image generation method, comprising: determining a focus correction coefficient corresponding to a first CT device based on the focus correction coefficient determination method described above, and generating a CT image based on the focus correction coefficient. Specifically, the focus correction coefficient corresponding to the first CT device can be determined based on the focus correction coefficient determination method described above, scanning data can be obtained by processing an electrical signal output by a first CT detector, the scan data can be corrected based on the focus correction coefficient, and an image can be reconstructed using the corrected scan data, thereby reconstructing a CT image with focus artifact correction.

[0083] Through the above steps, a CT image corrected for focus artifacts can be directly obtained without manually adjusting the focus correction coefficient of the first CT device, which saves time and labor costs and is easy to promote and apply in the image reconstruction process.

[0084] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0085] This embodiment also provides a device for determining a focus correction coefficient, which is used to implement the above-mentioned embodiments and preferred embodiments. Details already described are omitted. As used below, terms such as "module," "unit," and "subunit" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0086] Figure 6 is a structural block diagram of a device for determining a focus correction coefficient according to an embodiment of the present application, such as Figure 6 As shown, the device includes: a training data acquisition unit 201, a loss function construction unit 202, an output water model image acquisition unit 203, a model training unit 204 and a focus correction coefficient determination unit 205.

[0087] A training data acquisition unit 201 is configured to acquire training data; the training data includes water-based modeling data acquired based on a first CT device;

[0088] A loss function construction unit 202 is configured to construct a loss function based on a defocused water phantom image; the defocused water phantom image is a water phantom image with defocus artifacts;

[0089] an output water phantom image acquisition unit 203, configured to use the water phantom data as input to a pre-trained image generation model to obtain an output water phantom image based on the pre-trained image generation model;

[0090] A model training unit 204 is configured to calculate a loss value of the output water phantom image based on the loss function, and train the pre-trained image generation model until the loss value reaches a convergence threshold, thereby obtaining a fully trained image generation model;

[0091] The focus correction coefficient determining unit 205 is configured to determine the focus correction coefficient of the first CT device according to the model parameters of the image generation model obtained through training.

[0092] In some embodiments, the loss function construction unit 202 includes: a defocused water phantom image acquisition module, a region segmentation module, and a loss function acquisition module.

[0093] A defocused water phantom image acquisition module, used for acquiring a defocused water phantom image;

[0094] a region segmentation module, configured to segment the defocused water phantom image to obtain a water phantom main region and a water phantom wall region;

[0095] The loss function acquisition module is used to construct a loss function according to the difference in CT value distribution between the water phantom main area and the water phantom wall area.

[0096] In some embodiments, the loss function acquisition module is specifically used to:

[0097] The standard deviation between the CT mean of the water phantom main region and the CT mean of the water phantom wall region is determined as the loss function.

[0098] In some embodiments, the CT mean value of the water phantom main body region and / or the CT mean value of the water phantom wall region is a pixel mean value of a preset number of pixel points in the corresponding region.

[0099] In some embodiments, the focus correction coefficient determination unit 205 includes: a model parameter acquisition module and a focus correction coefficient determination module.

[0100] A model parameter acquisition module, configured to acquire corresponding model parameters according to the trained image generation model, wherein the model parameters include weights and biases;

[0101] A focus correction coefficient determination module is used to determine the focus correction coefficient of the first CT device according to the weight and the offset.

[0102] In some embodiments, the pre-trained image generation model is an image generation model trained based on a second CT device; the first CT device and the second CT device are of the same type.

[0103] This embodiment further provides a CT image generating device, including: a first CT image generating unit.

[0104] The first CT image generating unit is configured to determine an image generation model corresponding to the first CT device based on the focus correction coefficient determining method described above, and generate a CT image based on the image generation model.

[0105] This embodiment further provides another CT image generating device, including: a second CT image generating unit.

[0106] The second CT image generating unit is configured to determine a focus correction coefficient corresponding to the first CT device based on the focus correction coefficient determining method described above, and generate a CT image based on the focus correction coefficient.

[0107] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0108] In addition, the focus correction coefficient determination method or CT image generation method of the embodiment of the present application can be implemented by an electronic device. Figure 7 Schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application.

[0109] The electronic device may include a processor 31 and a memory 32 storing computer program instructions.

[0110] Specifically, the processor 31 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0111] Among them, the memory 32 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 32 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 32 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 32 may be inside or outside the data processing device. In a specific embodiment, the memory 32 is a non-volatile memory. In a specific embodiment, the memory 32 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0112] The memory 32 may be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 31 .

[0113] The processor 31 reads and executes computer program instructions stored in the memory 32 to implement any one of the focus correction coefficient determination methods or CT image generation methods in the above embodiments.

[0114] In some embodiments, the electronic device may further include a communication interface 33 and a bus 30. Figure 7 As shown, the processor 31 , the memory 32 , and the communication interface 33 are connected via a bus 30 and communicate with each other.

[0115] The communication interface 33 is used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present application. The communication interface 33 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0116] The bus 30 includes hardware, software, or both, and couples the components of the electronic device to each other. The bus 30 includes, but is not limited to, at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 30 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Bus 30 may include one or more buses, where appropriate. Although embodiments herein describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.

[0117] The electronic device can execute the focus correction coefficient determination method or CT image generation method in the embodiment of the present application based on the acquired program instructions.

[0118] In addition, in conjunction with the focus correction coefficient determination method or CT image generation method in the above-mentioned embodiments, embodiments of the present application may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the focus correction coefficient determination methods or CT image generation methods in the above-mentioned embodiments is implemented.

[0119] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0120] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for determining a focus correction coefficient, characterized in that: include: Acquire training data; the training data includes water model data acquired based on the first CT device; Acquire an off-focus water phantom image; Segmenting the defocused water phantom image to obtain a water phantom main region and a water phantom wall region; constructing a loss function based on a difference in CT value distribution between the water phantom main region and the water phantom wall region; the defocused water phantom image is a water phantom image with defocus artifacts; Using the water phantom data as input to a pre-trained image generation model to obtain an output water phantom image based on the pre-trained image generation model; Calculating a loss value of the output water phantom image based on the loss function, training the pre-trained image generation model until the loss value reaches a convergence threshold, and obtaining a fully trained image generation model; Determine a focus correction coefficient of the first CT device according to the model parameters of the image generation model obtained through training.

2. The method for determining a focus correction coefficient according to claim 1, wherein: The constructing of the loss function according to the difference in CT value distribution between the water phantom main region and the water phantom wall region includes: The standard deviation between the CT mean of the water phantom main region and the CT mean of the water phantom wall region is determined as the loss function.

3. The method for determining the focus correction coefficient according to claim 2, wherein: The CT mean value of the water model main body area and / or the CT mean value of the water model wall area is the pixel mean of a preset number of pixel points in the corresponding area.

4. The method for determining a focus correction coefficient according to claim 1, wherein: Determining the focus correction coefficient of the first CT device according to the model parameters of the image generation model obtained through training includes: Obtaining corresponding model parameters according to the image generation model obtained through training, wherein the model parameters include weights and biases; A focus correction coefficient of the first CT device is determined according to the weight and the offset.

5. The method for determining a focus correction coefficient according to claim 1, wherein: The pre-trained image generation model is an image generation model trained based on a second CT device; the first CT device and the second CT device are of the same type.

6. A CT image generation method, characterized in that: include: Determine an image generation model corresponding to the first CT device based on the method for determining the focus correction coefficient according to any one of claims 1 to 5, and generate a CT image based on the image generation model; or A focus correction coefficient corresponding to a first CT device is determined based on the focus correction coefficient determination method according to any one of claims 1 to 5, and a CT image is generated based on the focus correction coefficient.

7. A device for determining a focus correction coefficient, characterized in that: include: A training data acquisition unit, configured to acquire training data; the training data includes water modeling data acquired based on the first CT device; a loss function construction unit configured to obtain a defocused water phantom image; segment the defocused water phantom image to obtain a water phantom main region and a water phantom wall region; and construct a loss function based on a difference in CT value distribution between the water phantom main region and the water phantom wall region; the defocused water phantom image being a water phantom image with defocus artifacts; an output water phantom image acquisition unit, configured to use the water phantom data as input to a pre-trained image generation model to obtain an output water phantom image based on the pre-trained image generation model; a model training unit, configured to calculate a loss value of the output water phantom image based on the loss function, and train the pre-trained image generation model until the loss value reaches a convergence threshold, thereby obtaining a fully trained image generation model; A focus correction coefficient determination unit is used to determine the focus correction coefficient of the first CT device according to the model parameters of the image generation model obtained through training.

8. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the focus correction coefficient determination method according to any one of claims 1 to 5 or the CT image generation method according to claim 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining a focus correction coefficient according to any one of claims 1 to 5 or the method for generating a CT image according to claim 6 is implemented.

Images